New recommendation techniques for multicriteria rating systems

Gediminas Adomavicius, Young Ok Kwon

Research output: Contribution to journalArticlepeer-review

310 Scopus citations

Abstract

Several new approaches for extending recommendation technologies to incorporate and leverage multicriteria rating information are presented. Personalization technologies and recommender systems help online consumers avoid information overload by making suggestions regarding which information is most relevant to them. Recommender systems are usually classified according to their recommendation approach including, content-based approaches, collaborative filtering, and hybrid approaches. The overall rating that users give to an item provides the information regarding how much they like the item, and multicriteria ratings provide some insights regarding why they like it. Therefore, multicriteria ratings enable more accurate estimates of the similarity between two users. A new method is proposed to extend the standard collaborative-filtering algorithm to include multicriteria rating.

Original languageEnglish (US)
Pages (from-to)48-55
Number of pages8
JournalIEEE Intelligent Systems
Volume22
Issue number3
DOIs
StatePublished - May 2007

Bibliographical note

Funding Information:
The US National Science Foundation supported part of the research reported in this article under grant IIS-0546443.

Fingerprint

Dive into the research topics of 'New recommendation techniques for multicriteria rating systems'. Together they form a unique fingerprint.

Cite this